mihirp1998 / AlignPropLinks
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
☆291Updated 8 months ago
Alternatives and similar repositories for AlignProp
Users that are interested in AlignProp are comparing it to the libraries listed below
Sorting:
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆233Updated last year
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆527Updated 5 months ago
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆341Updated 9 months ago
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆234Updated 3 months ago
- GenEval: An object-focused framework for evaluating text-to-image alignment☆323Updated 4 months ago
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆143Updated 5 months ago
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆278Updated 3 months ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆292Updated 8 months ago
- (CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision☆126Updated 6 months ago
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆138Updated last year
- [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation☆271Updated 3 months ago
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆290Updated 4 months ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆286Updated 2 years ago
- 🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)☆179Updated last year
- [WACV 2024] Training-Free Layout Control with Cross-Attention Guidance☆258Updated last year
- The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utility☆55Updated 5 months ago
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]☆170Updated 3 months ago
- SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training☆182Updated 5 months ago
- MoVQGAN - model for the image encoding and reconstruction☆240Updated last year
- ☆111Updated 5 months ago
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆537Updated last year
- ☆521Updated 6 months ago
- Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"☆408Updated last year
- [NeurIPS 2024] CV-VAE: A Compatible Video VAE for Latent Generative Video Models☆276Updated 7 months ago
- [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy☆252Updated 7 months ago
- ☆126Updated last year
- Official codebase for the Paper “Retrieval-Augmented Diffusion Models”☆133Updated 2 years ago
- An implementation of the Prompt-to-Prompt paper for the SDXL architecture☆112Updated last year
- Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.☆341Updated last year
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆143Updated 4 months ago